PSC-CPI: Multi-Scale Protein Sequence-Structure Contrasting for Efficient and Generalizable Compound-Protein Interaction Prediction

TL;DR

PSC-CPI introduces a multi-scale contrastive learning framework that jointly models protein sequences and structures at various scales, improving compound-protein interaction prediction especially in challenging scenarios with unseen data or missing modalities.

Contribution

The paper presents a novel multi-scale contrastive framework for CPI prediction that effectively models intra- and cross-modality dependencies across multiple scales, enhancing generalization and robustness.

Findings

PSC-CPI outperforms existing methods in all test settings.

The model maintains strong performance with missing modality data.

Multi-scale contrastive learning improves prediction accuracy in complex scenarios.

Abstract

Compound-Protein Interaction (CPI) prediction aims to predict the pattern and strength of compound-protein interactions for rational drug discovery. Existing deep learning-based methods utilize only the single modality of protein sequences or structures and lack the co-modeling of the joint distribution of the two modalities, which may lead to significant performance drops in complex real-world scenarios due to various factors, e.g., modality missing and domain shifting. More importantly, these methods only model protein sequences and structures at a single fixed scale, neglecting more fine-grained multi-scale information, such as those embedded in key protein fragments. In this paper, we propose a novel multi-scale Protein Sequence-structure Contrasting framework for CPI prediction (PSC-CPI), which captures the dependencies between protein sequences and structures through both intra-modality and cross-modality contrasting. We further apply length-variable protein augmentation to allow contrasting to be performed at different scales, from the amino acid level to the sequence level. Finally, in order to more fairly evaluate the model generalizability, we split the test data into four settings based on whether compounds and proteins have been observed during the training stage. Extensive experiments have shown that PSC-CPI generalizes well in all four settings, particularly in the more challenging ``Unseen-Both" setting, where neither compounds nor proteins have been observed during training. Furthermore, even when encountering a situation of modality missing, i.e., inference with only single-modality protein data, PSC-CPI still exhibits comparable or even better performance than previous approaches.